Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to attributes and properties in programming or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    attribute, property, setting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikiseite
    -0.47
     Spitze
    -0.44
     contemporáneo
    -0.43
     vieja
    -0.42
     držav
    -0.41
     contemporánea
    -0.40
     navidad
    -0.39
    posób
    -0.39
     biała
    -0.39
     Überblick
    -0.39
    POSITIVE LOGITS
     autorytatywna
    0.67
    rungsseite
    0.61
     ComVisible
    0.61
    PyExc
    0.57
     ujednoznacz
    0.55
     estekak
    0.55
    Personensuche
    0.54
    يكب
    0.53
     saites
    0.52
     nahilalakip
    0.52
    Act Density 0.000%

    No Known Activations